Ethon Lin
Ethon Lin
About
- Username
- Ethon Lin
- Joined
- Visits
- 1,278
- Last Active
- Roles
- Member, ModeratorsKL520, ModeratorsKL720, ModeratorsAIModel
Comments
-
若是重新插拔以及在Windows環境下也是一樣的問題，那應該就是dongle本身有損壞需要進一步的分析，還請向電腦公會申請更換，聯絡方式如下 電腦公會的湯小姐 justine_tang@mail.tca.org.tw 02-2577-4249 #390
-
請問，將dongle插拔後再試結果還是一樣嗎? 是否會有windows環境也可以試試看是否一樣的現象呢?
-
https://www.kneron.com/forum/discussion/comment/334#Comment_334 因為使用的是KL520的dongle，指令的部分還請加上 KL520，完整指令如下 python main.py -t KL520-update_fw https://www.kneron.com/forum/uploads/007/K60QV1S8SN6D.jpg
-
Hello, "add device failed" 表示電腦端透過host_lib這包程式跟dongle的溝通失敗了，所以無法做進一步的應用。因這樣的錯誤有很多可能性，所以想請你幫忙檢查下面的項目 dongle的購買來源是? 時間點大約為何時? 環境中是否有安裝libusb (apt install libusb-…
-
The two models LittleNet.onnx and LittleNet_convert.onnx are different. That's why you got different result. The weight between this 2 models are different https://www.kneron.com/forum/uploads/066/8RJBHD6KBH4Y.png And the op-type of the last layers …
-
Hi Denis, It means the operator deconvolution could be used in KL520 and our compiler will use upsampling + conv to implement the operator. So you don't need to do other operation with the layer deconvolution.
-
As the photo below, the output of LittleNet.onnx is a array with dimension 2x1x1. And you will get different inference result with different image input. https://www.kneron.com/forum/uploads/538/971ACVSY3PQH.jpg If you want to run your own model, …
-
https://www.kneron.com/forum/discussion/110/importerror-no-module-named-ktc The ktc module is a library of python, so you should use ktc module in python only. You can import it in your python file like "/workspace/examples/LittleNet/python_api…
-
It's Cyclic redundancy check. The api is used for getting the CRC of model data, to make sure the data transportation is successful. You can find the information from our document center. http://doc.kneron.com/docs/#host_lib_1.0.0/kdp_host.h/#kdp_g…
-
Could you provide more specific information for clarifying the issue? Like what kind of commands you had used, which command makes you meet the error, and the full error message you encountered, etc.
-
https://www.kneron.com/forum/discussion/comment/312#Comment_312 The control flow of NPU is "host_lib <-> scpu <-> npuc <-> NPU". And there are 2 ways to get inference with your image and model, "DME mode" and &…
-
About your question: 1. Did you provide any API to get the AI Dongle's run-time hardware usage information? What kind of information you want to get? You can find all corresponding APIs from following link. http://doc.kneron.com/docs/#host_lib_1.0.…
-
Hello, As you mentioned the result of RGB565 was right but RGBA8888 (you bypass preprocess and implement by yourself) was wrong. I think the issue could be related to image format. Here is the format of RGB565, RGBA8888 and bypass preprocess https:/…
-
The *.bie is a quantized model, you can run it on End to End Simulator. http://doc.kneron.com/docs/#toolchain/python_app/app_flow_manual/ And the *.nef is a model format for kneron dongle (KL520/ KL720), which was compiled from *.bie. To run inferen…
-
Once run with out of memory, the system could keep on some memory issues still. Please exit from the docker environment, re-login and use 1 image case retry again.
-
Sorry but I don't understand your question. Could you show more details about your issue? Including the command you used, full error message, and so on. And it will be helpful if you could provide your onnx file. Did you successfully get the convert…
-
Hi Raef, I think the issue was caused of the input dimension 1x12x160x160. Kneron's toolchain doesn't support 12-channel input and run image preprocess with 3 channels as default setting. That's why the error message showed got 76800 lines ( 3x160 …
-
Hi Angie, I checked your model and found out the issue is caused by the dimension 16x3x224x224. We see the first degree "16" as batch_size, and the KL520 / KL720 only support the case whose batch_size is 1. (e.g. 1x3x224x224) That's why …
-
Hi Tim, Would you please provide the onnx or h5 for debug?
-
Have ever checked the image you set in json? It seems there are some issues in model input. Input file dimension is not correct: expected: 2408448, but got: 150528 lines. /workspace/.tmp/input.1/ILSVRC2012_val_00000003.txt
-
Hi, If you want to remove the op softmax, you can refer to the 3.1.7 Model Editor in Toolchain Manual http://doc.kneron.com/docs/#toolchain/manual/. And try onnx2onnx again to check your model after cutting the layer softmax.
-
I think the error was caused by preprocess error. Did you revised the customer part in img_preprocess.py? "img_preprocess_method": "customized", <= the setting means you want to customize your own preprocess. Ple…
-
I think the problem is that you didn't specify the path of model you want to inference. Please run “ex_kdp2_generic_inference” with arguments -p, -d, and -m to specify the path of your NEF. And the step 3 of your list is for another purpose, it's …
-
有關batchcompile的做法現在剩兩種 http://doc.kneron.com/docs/#toolchain/manual/#3-toolchain-scripts-usage 連結中的3.5 Batch-Compile，此步驟會需要先執行3.2 FpAnalyser, Compiler and IpEvaluator產生*.bie，然後在input_batch_compile.json中填入id, version…
-
Now your code flow is : inf_res, paf = ktc.kneron_inference(img_data, nef_file=compile_result, radix=ktc.get_radix([img_data])) Please change it into : inf_res = ktc.kneron_inference(img_data, nef_file=compile_result, radix=ktc.get_radix([i…
-
Because kneron_inference only has one output, it would got error if you two variables to get its output. The output of the kneron_inference would be the results of the model output nodes. For example, the output node of the model "output.onnx&q…
-
有關NEF生成的部分，Toolchain v0.14.1的步驟為新的做法，http://doc.kneron.com/docs/#520_1.4.0.0/getting_start/#520_1.4.0.0/getting_start/的6.3為舊的作法，需要正確的填寫兩個json的設定才可以生成NEF，但兩種做法結果是一樣的，擇一即可 而fw_scpu.bin與fw_ncp…
-
Yes, the model_id 19 is for Kneron's tiny yolo v3 example. But the NEF is just 88Kb, so I guess the model you generated is not tiny yolo v3. Was the NEF file generated by command "fpAnalyserCompilerIpevaluator_520.py" and "batchCompil…
-
It seems the firmware system got something after load your NEF model. How many models in your NEF file? Is any model with model_id 19 in the NEF file. And how large your NEF file is?
-
KL520 could be used with RK3399, but the usb command of KL520 is transferred by libusb. https://github.com/libusb/libusb/releases/tag/v1.0.23 User should make sure the libusb could work on their own environment.